Analizing Doublets with UMAP
2022-01-14
1 Introduction
In this notebook we will plot the scrublet doublet scores on the UMAPs computed in the previous notebook.
2 Pre-processing
2.1 Load packages
library(Seurat)## Attaching SeuratObjectlibrary(Signac)
library(tidyverse)## Registered S3 method overwritten by 'cli':
## method from
## print.boxx spatstat.geom## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──## ✓ ggplot2 3.3.5 ✓ purrr 0.3.4
## ✓ tibble 3.1.6 ✓ dplyr 1.0.7
## ✓ tidyr 1.1.4 ✓ stringr 1.4.0
## ✓ readr 2.1.1 ✓ forcats 0.5.1## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
## x purrr::reduce() masks Signac::reduce()2.2 Load data
# Paths
path_to_data <-("/Users/mlromeror/Documents/multiome_tonsil_Lucia/results/R_objects/8.tonsil_multiome_integrated_using_wnn.rds")
tonsil_integrated <- readRDS(path_to_data)2.3 Parameters
# Thresholds
max_doublet_score_rna <- 0.33 Doublet score
3.1 Scrublet doublet score
hist <- tonsil_integrated@meta.data %>%
ggplot(aes(doublet_scores)) +
geom_histogram(bins = 30) +
geom_vline(
xintercept = 0.3,
linetype = "dashed",
color = "red"
) +
xlab("Doublet Score (RNA)") +
theme_bw() +
theme(
axis.title = element_text(size = 13),
axis.text = element_text(size = 11)
)
hist
3.2 Projection
3.2.1 RNA-driven UMAP
# Plot
feat_plot1 <- FeaturePlot(
tonsil_integrated,
features = "doublet_scores",
reduction = "umap.atac",
pt.size = 0.1
)+ ggtitle('scATAC UMAP doublet scores')
dim_plot1 <- DimPlot(
tonsil_integrated,
group.by = "predicted_doublets",
reduction = "umap.atac",
pt.size = 0.1
) + ggtitle('scATAC UMAP predicted doublet') feat_plot1
dim_plot1
3.2.2 RNA-driven UMAP
feat_plot3 <- FeaturePlot(
tonsil_integrated,
features = "doublet_scores",
reduction = "umap.rna",
pt.size = 0.1
) + ggtitle('scRNA UMAP doublet scores')
dim_plot2 <- DimPlot(
tonsil_integrated,
group.by = "predicted_doublets",
reduction = "umap.rna",
pt.size = 0.1
)+ ggtitle('scRNA UMAP predicted doublets ') feat_plot3
dim_plot2
3.3 Joint Multiome
feat_plot4 <- FeaturePlot(
tonsil_integrated,
features = "doublet_scores",
reduction = "umap",
pt.size = 0.1
)+ ggtitle('Joint UMAP doublet scores')
dim_plot4 <- DimPlot(
tonsil_integrated,
group.by = "predicted_doublets",
reduction = "umap",
pt.size = 0.1
)+ ggtitle('Joint UMAP predicted doublets') feat_plot4
dim_plot4
4 Session Information
sessionInfo()## R version 4.1.2 (2021-11-01)
## Platform: x86_64-apple-darwin17.0 (64-bit)
## Running under: macOS Big Sur 10.16
##
## Matrix products: default
## BLAS: /Library/Frameworks/R.framework/Versions/4.1/Resources/lib/libRblas.0.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.1/Resources/lib/libRlapack.dylib
##
## locale:
## [1] es_ES.UTF-8/es_ES.UTF-8/es_ES.UTF-8/C/es_ES.UTF-8/es_ES.UTF-8
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] forcats_0.5.1 stringr_1.4.0 dplyr_1.0.7 purrr_0.3.4
## [5] readr_2.1.1 tidyr_1.1.4 tibble_3.1.6 ggplot2_3.3.5
## [9] tidyverse_1.3.1 Signac_1.5.0 SeuratObject_4.0.4 Seurat_4.0.6
## [13] BiocStyle_2.22.0
##
## loaded via a namespace (and not attached):
## [1] readxl_1.3.1 backports_1.4.1 fastmatch_1.1-3
## [4] plyr_1.8.6 igraph_1.2.10 lazyeval_0.2.2
## [7] splines_4.1.2 BiocParallel_1.28.3 listenv_0.8.0
## [10] scattermore_0.7 SnowballC_0.7.0 GenomeInfoDb_1.30.0
## [13] digest_0.6.29 htmltools_0.5.2 magick_2.7.3
## [16] fansi_0.5.0 magrittr_2.0.1 tensor_1.5
## [19] cluster_2.1.2 ROCR_1.0-11 tzdb_0.2.0
## [22] globals_0.14.0 Biostrings_2.62.0 modelr_0.1.8
## [25] matrixStats_0.61.0 docopt_0.7.1 spatstat.sparse_2.1-0
## [28] colorspace_2.0-2 rvest_1.0.2 ggrepel_0.9.1
## [31] haven_2.4.3 xfun_0.29 sparsesvd_0.2
## [34] crayon_1.4.2 RCurl_1.98-1.5 jsonlite_1.7.2
## [37] spatstat.data_2.1-2 survival_3.2-13 zoo_1.8-9
## [40] glue_1.6.0 polyclip_1.10-0 gtable_0.3.0
## [43] zlibbioc_1.40.0 XVector_0.34.0 leiden_0.3.9
## [46] future.apply_1.8.1 BiocGenerics_0.40.0 abind_1.4-5
## [49] scales_1.1.1 DBI_1.1.1 miniUI_0.1.1.1
## [52] Rcpp_1.0.7 viridisLite_0.4.0 xtable_1.8-4
## [55] reticulate_1.22 spatstat.core_2.3-2 stats4_4.1.2
## [58] htmlwidgets_1.5.4 httr_1.4.2 RColorBrewer_1.1-2
## [61] ellipsis_0.3.2 ica_1.0-2 pkgconfig_2.0.3
## [64] farver_2.1.0 dbplyr_2.1.1 sass_0.4.0
## [67] ggseqlogo_0.1 uwot_0.1.11 deldir_1.0-6
## [70] utf8_1.2.2 labeling_0.4.2 tidyselect_1.1.1
## [73] rlang_0.4.12 reshape2_1.4.4 later_1.3.0
## [76] cellranger_1.1.0 munsell_0.5.0 tools_4.1.2
## [79] cli_3.1.0 generics_0.1.1 broom_0.7.10
## [82] ggridges_0.5.3 evaluate_0.14 fastmap_1.1.0
## [85] yaml_2.2.1 goftest_1.2-3 fs_1.5.2
## [88] knitr_1.36 fitdistrplus_1.1-6 RANN_2.6.1
## [91] pbapply_1.5-0 future_1.23.0 nlme_3.1-153
## [94] mime_0.12 slam_0.1-49 RcppRoll_0.3.0
## [97] xml2_1.3.3 rstudioapi_0.13 compiler_4.1.2
## [100] plotly_4.10.0 png_0.1-7 spatstat.utils_2.3-0
## [103] reprex_2.0.1 tweenr_1.0.2 bslib_0.3.1
## [106] stringi_1.7.6 highr_0.9 lattice_0.20-45
## [109] Matrix_1.3-4 vctrs_0.3.8 pillar_1.6.4
## [112] lifecycle_1.0.1 BiocManager_1.30.16 spatstat.geom_2.3-1
## [115] lmtest_0.9-39 jquerylib_0.1.4 RcppAnnoy_0.0.19
## [118] data.table_1.14.2 cowplot_1.1.1 bitops_1.0-7
## [121] irlba_2.3.5 httpuv_1.6.4 patchwork_1.1.1
## [124] GenomicRanges_1.46.1 R6_2.5.1 bookdown_0.24
## [127] promises_1.2.0.1 KernSmooth_2.23-20 gridExtra_2.3
## [130] lsa_0.73.2 IRanges_2.28.0 parallelly_1.30.0
## [133] codetools_0.2-18 MASS_7.3-54 assertthat_0.2.1
## [136] withr_2.4.3 qlcMatrix_0.9.7 sctransform_0.3.2
## [139] Rsamtools_2.10.0 S4Vectors_0.32.3 GenomeInfoDbData_1.2.7
## [142] hms_1.1.1 mgcv_1.8-38 parallel_4.1.2
## [145] grid_4.1.2 rpart_4.1-15 rmarkdown_2.11
## [148] Rtsne_0.15 ggforce_0.3.3 lubridate_1.8.0
## [151] shiny_1.7.1